© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13572
    Prev
    Next
    INDEX
    Explanations

    timestamps and usernames within a discussion forum

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    160
    +0.14
    0.5%
    640
    +0.14
    0.5%
    365
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.14
    0.06
    640
    +0.14
    0.05
    627
    +0.13
    0.04
    Negative Logits
    heit
    -1.00
    icum
    -0.99
    packages
    -0.91
    inyl
    -0.89
    wagen
    -0.89
    obyl
    -0.86
    redients
    -0.85
    nut
    -0.85
    afety
    -0.84
    ileaks
    -0.84
    POSITIVE LOGITS
    Introduced
    0.95
    asio
    0.94
    video
    0.87
    ZI
    0.86
    Video
    0.85
    Fra
    0.85
    AAA
    0.84
    Uncommon
    0.84
    gged
    0.82
    II
    0.81
    Activations Density 0.147%

    No Known Activations